To keep the competition focused, the participants of the CATS4ML challenge will search for adverse example images only in the target images and for the target labels provided below:

• Target images: These are the subset of images from Open Images Dataset (OID). Only image IDs from these target images will be considered for this challenge.
  • Please note we have updated the target images dataset.
  • Please use this new_target_images_large.csv.
  • The old file target_images_large.csv does not contain all the images. If you have already downloaded it, please update it with the new file.
• Target labels: a list of the labels for which participants should find adverse examples (AI blindspots).

Check Participate to learn how to start contributing.